Nexus-VMC-v1.4-RCL (1.5B) - Unified Strategic Intelligence

Nexus-VMC-v1.4-RCL is a high-performance Small Language Model (SLM) meticulously fine-tuned for the Antigravity Hub. It excels in medical reasoning, Excel data logic, and complex tool-calling via the VMC-RCL (Reasoning-Call-Logic) protocol.

Key Features

• Strategic Reasoning: Native support for <vmc_think> blocks, enabling deep analytical processing before task execution.
• Precision Tool-Calling: 100% adherence to [TOOL_CALL] JSON schemas in comparative benchmarking.
• Unified Domain Mastery: Expert-level performance in Medical clinical reasoning, Excel formula generation (SUMIF, etc.), and Document RAG.
• Ultra-Efficient Inference: Optimized for local deployment on 8GB RAM environments (Laptop GPUs, CPU inference).

Benchmark Results (Phase 1.4 RCL)

Benchmarked against SLM baselines and 9B-class models on a 4070 Laptop GPU (Ollama API).

Model	Avg TPS	Med Reasoning	Excel Logic	Hub Protocol Adherence
Nexus-VMC-v1.4-RCL	130.3	PASS (Strategic)	PASS (SUMIF)	Native (S-Tier)
hauhau-qwen9b	37.2	PASS (Text)	PASS (Text)	B-Tier
phi3.5:latest	94.1	PARTIAL (Python)	PASS (Formula)	C-Tier
qwen2.5:1.5b	196.4	FAIL (Manual)	FAIL (Repeated)	D-Tier

Usage Examples

VMC-RCL Protocol

User: 병원의 재원 할당을 최적화하기 위해 현재 환자 수를 분석해줘.

Assistant:
<vmc_think>
환자 수 데이터를 기반으로 한 최적화 분석이 필요함. 
hospital_warehouse 도구를 호출하여 실시간 데이터를 가져오는 논리적 흐름 설정.
</vmc_think>
[TOOL_CALL]
{"name": "mcp_tool", "kwargs": {"target": "hospital_warehouse", "query": "current_patient_census"}}

How to Run locally (Ollama)

1. Download the nexus-vmc-v1.4.Q8_0.gguf file.
2. Create a Modelfile:

   FROM ./nexus-vmc-v1.4.Q8_0.gguf
   TEMPLATE "<|im_start|>user\n{{ .Prompt }}<|im_end|>\n<|im_start|>assistant\n"
   PARAMETER stop "<|im_end|>"
   

3. Run ollama create nexus-v1.4 -f Modelfile
4. Run ollama run nexus-v1.4

License

Apache 2.0